.gitignore

@@ -1,40 +0,0 @@
-*.csv
-*.yaml
-*.xlsx
-*.pdf
-*.txt
-*.log
-*.pyc
-/chatchat_data.bak
-/chatchat_data/data/knowledge_base/samples
-/chatchat_data
-.idea/inspectionProfiles/profiles_settings.xml
-.idea/Langchain-Chatchat.iml
-.idea/misc.xml
-.idea/modules.xml
-.idea/prettier.xml
-.idea/vcs.xml
-.idea/inspectionProfiles/profiles_settings.xml
-.idea/Langchain-Chatchat.iml
-.idea/modules.xml
-.idea/prettier.xml
-.idea/vcs.xml
-/.idea
-/test_tool
-chatchat_data/tool_settings.yaml
-chatchat_data/prompt_settings.yaml
-chatchat_data/model_settings.yaml
-chatchat_data/basic_settings.yaml
-localconfig/data/knowledge_base/samples/content/分布式训练技术原理.md
-localconfig/data/knowledge_base/samples/content/大模型应用技术原理.md
-localconfig/data/knowledge_base/samples/content/大模型技术栈-实战与应用.md
-localconfig/data/knowledge_base/samples/content/大模型技术栈-算法与原理.md
-localconfig/data/knowledge_base/samples/content/大模型指令对齐训练原理.md
-localconfig/data/knowledge_base/samples/content/大模型推理优化策略.md
-localconfig/data/knowledge_base/samples/vector_store/bge-large-zh-v1.5/index.faiss
-localconfig/data/knowledge_base/samples/vector_store/bge-large-zh-v1.5/index.pkl
-localconfig/data/knowledge_base/info.db
-chatchat_data/basic_settings.yaml
-chatchat_data/model_settings.yaml
-chatchat_data/prompt_settings.yaml
-chatchat_data/tool_settings.yaml

.idea/.gitignore

@@ -1,8 +0,0 @@
-# 默认忽略的文件
-/shelf/
-/workspace.xml
-# 基于编辑器的 HTTP 客户端请求
-/httpRequests/
-# Datasource local storage ignored files
-/dataSources/
-/dataSources.local.xml

.idea/dictionaries/Guan.xml

@@ -1,7 +0,0 @@
-<component name="ProjectDictionaryState">
-  <dictionary name="Guan">
-    <words>
-      <w>aggrid</w>
-    </words>
-  </dictionary>
-</component>

chatchat_data/model_settings.yaml

@@ -2,7 +2,7 @@
 
 
 # 默认选用的 LLM 名称
-DEFAULT_LLM_MODEL: qwen2.5-instruct
+DEFAULT_LLM_MODEL: qwen2-instruct
 
 # 默认选用的 Embedding 名称
 DEFAULT_EMBEDDING_MODEL: bge-large-zh-v1.5
@@ -112,78 +112,78 @@ LLM_MODEL_CONFIG:
 MODEL_PLATFORMS:
   - platform_name: xinference
     platform_type: xinference
-    api_base_url: http://192.168.0.21:9997/v1
+    api_base_url: http://127.0.0.1:9997/v1
     api_key: EMPTY
     api_proxy: ''
     api_concurrencies: 5
     auto_detect_model: true
-    llm_models: [qwen2.5-instruct]
+    llm_models: []
-    embed_models: [bge-large-zh-v1.5]
+    embed_models: []
+    text2image_models: []
+    image2text_models: []
+    rerank_models: [bge-reranker-large]
+    speech2text_models: []
+    text2speech_models: []
+  - platform_name: ollama
+    platform_type: ollama
+    api_base_url: http://127.0.0.1:11434/v1
+    api_key: EMPTY
+    api_proxy: ''
+    api_concurrencies: 5
+    auto_detect_model: false
+    llm_models:
+      - qwen:7b
+      - qwen2:7b
+    embed_models:
+      - quentinz/bge-large-zh-v1.5
+    text2image_models: []
+    image2text_models: []
+    rerank_models: []
+    speech2text_models: []
+    text2speech_models: []
+  - platform_name: oneapi
+    platform_type: oneapi
+    api_base_url: http://127.0.0.1:3000/v1
+    api_key: sk-
+    api_proxy: ''
+    api_concurrencies: 5
+    auto_detect_model: false
+    llm_models:
+      - chatglm_pro
+      - chatglm_turbo
+      - chatglm_std
+      - chatglm_lite
+      - qwen-turbo
+      - qwen-plus
+      - qwen-max
+      - qwen-max-longcontext
+      - ERNIE-Bot
+      - ERNIE-Bot-turbo
+      - ERNIE-Bot-4
+      - SparkDesk
+    embed_models:
+      - text-embedding-v1
+      - Embedding-V1
+    text2image_models: []
+    image2text_models: []
+    rerank_models: []
+    speech2text_models: []
+    text2speech_models: []
+  - platform_name: openai
+    platform_type: openai
+    api_base_url: https://api.openai.com/v1
+    api_key: sk-proj-
+    api_proxy: ''
+    api_concurrencies: 5
+    auto_detect_model: false
+    llm_models:
+      - gpt-4o
+      - gpt-3.5-turbo
+    embed_models:
+      - text-embedding-3-small
+      - text-embedding-3-large
     text2image_models: []
     image2text_models: []
     rerank_models: []
     speech2text_models: []
     text2speech_models: []
-#  - platform_name: ollama
-#    platform_type: ollama
-#    api_base_url: http://127.0.0.1:11434/v1
-#    api_key: EMPTY
-#    api_proxy: ''
-#    api_concurrencies: 5
-#    auto_detect_model: false
-#    llm_models:
-#      - qwen:7b
-#      - qwen2:7b
-#    embed_models:
-#      - quentinz/bge-large-zh-v1.5
-#    text2image_models: []
-#    image2text_models: []
-#    rerank_models: []
-#    speech2text_models: []
-#    text2speech_models: []
-#  - platform_name: oneapi
-#    platform_type: oneapi
-#    api_base_url: http://127.0.0.1:3000/v1
-#    api_key: sk-
-#    api_proxy: ''
-#    api_concurrencies: 5
-#    auto_detect_model: false
-#    llm_models:
-#      - chatglm_pro
-#      - chatglm_turbo
-#      - chatglm_std
-#      - chatglm_lite
-#      - qwen-turbo
-#      - qwen-plus
-#      - qwen-max
-#      - qwen-max-longcontext
-#      - ERNIE-Bot
-#      - ERNIE-Bot-turbo
-#      - ERNIE-Bot-4
-#      - SparkDesk
-#    embed_models:
-#      - text-embedding-v1
-#      - Embedding-V1
-#    text2image_models: []
-#    image2text_models: []
-#    rerank_models: []
-#    speech2text_models: []
-#    text2speech_models: []
-#  - platform_name: openai
-#    platform_type: openai
-#    api_base_url: https://api.openai.com/v1
-#    api_key: sk-proj-
-#    api_proxy: ''
-#    api_concurrencies: 5
-#    auto_detect_model: false
-#    llm_models:
-#      - gpt-4o
-#      - gpt-3.5-turbo
-#    embed_models:
-#      - text-embedding-3-small
-#      - text-embedding-3-large
-#    text2image_models: []
-#    image2text_models: []
-#    rerank_models: []
-#    speech2text_models: []
-#    text2speech_models: []

chatchat_data/tool_settings.yaml

@@ -14,7 +14,7 @@ search_local_knowledgebase:
 # 搜索引擎工具配置项。推荐自己部署 searx 搜索引擎，国内使用最方便。
 search_internet:
   use: false
-  search_engine_name: zhipu_search
+  search_engine_name: searx
   search_engine_config:
     bing:
       bing_search_url: https://api.bing.microsoft.com/v7.0/search
@@ -30,14 +30,6 @@ search_internet:
       engines: []
       categories: []
       language: zh-CN
-    tavily:
-      tavily_api_key: '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'
-      include_answer: true
-      search_depth: advanced
-      include_raw_content: True
-      max_results: 1
-    zhipu_search:
-      zhipu_api_key: 'e2bdc39618624fd782ebcd721185645c.pcvcrTPFT69Jda8B'
   top_k: 5
   verbose: Origin
   conclude_prompt: "<指令>这是搜索到的互联网信息，请你根据这些信息进行提取并有调理，简洁的回答问题。如果无法从中得到答案，请说 “无法搜索到能回答问题的内容”。

cudatest.py

@@ -13,6 +13,6 @@ print(f"cuDNN 版本: {cudnn_version}")
 
 # 检查是否可以访问 CUDA
 if torch.cuda.is_available():
-    print("pip install sentence-transformers -i https://pypi.mirrors.ustc.edu.cn/simpleCUDA is available. GPU name:", torch.cuda.get_device_name(0))
+    print("CUDA is available. GPU name:", torch.cuda.get_device_name(0))
 else:
     print("CUDA is not available. Please check your installation.")

libs/chatchat-server/chatchat/server/agent/tools_factory/search_internet.py

@@ -1,8 +1,5 @@
-import json
-import uuid
 from typing import Dict, List
 
-import requests
 from langchain.docstore.document import Document
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.utilities.bing_search import BingSearchAPIWrapper
@@ -10,21 +7,15 @@ from langchain.utilities.duckduckgo_search import DuckDuckGoSearchAPIWrapper
 from langchain.utilities.searx_search import SearxSearchWrapper
 from markdownify import markdownify
 from strsimpy.normalized_levenshtein import NormalizedLevenshtein
-from langchain_community.tools.tavily_search import TavilySearchResults
-import os
 
 from chatchat.settings import Settings
 from chatchat.server.pydantic_v1 import Field
 from chatchat.server.utils import get_tool_config
-from chatchat.utils import build_logger
-# from tavily import TavilyClient
 
 from .tools_registry import BaseToolOutput, regist_tool, format_context
 
-logger = build_logger()
 
-
+def searx_search(text ,config, top_k: int):
-def searx_search(text, config, top_k: int):
     print(f"searx_search: text: {text},config:{config},top_k:{top_k}")
     search = SearxSearchWrapper(
         searx_host=config["host"],
@@ -35,7 +26,7 @@ def searx_search(text, config, top_k: int):
     return search.results(text, top_k)
 
 
-def bing_search(text, config, top_k: int):
+def bing_search(text, config, top_k:int):
     search = BingSearchAPIWrapper(
         bing_subscription_key=config["bing_key"],
         bing_search_url=config["bing_search_url"],
@@ -43,7 +34,7 @@ def bing_search(text, config, top_k: int):
     return search.results(text, top_k)
 
 
-def duckduckgo_search(text, config, top_k: int):
+def duckduckgo_search(text, config, top_k:int):
     search = DuckDuckGoSearchAPIWrapper()
     return search.results(text, top_k)
 
@@ -51,7 +42,7 @@ def duckduckgo_search(text, config, top_k: int):
 def metaphor_search(
     text: str,
     config: dict,
-        top_k: int
+    top_k:int
 ) -> List[Dict]:
     from metaphor_python import Metaphor
 
@@ -94,77 +85,21 @@ def metaphor_search(
     return docs
 
 
-def tavily_search(text, config, top_k):
-    # 配置tavily api key
-    os.environ["TAVILY_API_KEY"] = config["tavily_api_key"]
-    # 初始化工具（配置参数）
-    tavily_tool = TavilySearchResults(
-        include_answer=config["include_answer"],  # 关键参数：启用答案生成
-        search_depth=config["search_depth"],  # 必须使用高级搜索模式
-        include_raw_content=config["include_raw_content"],
-        max_results=config["max_results"]
-    )
-
-    # 直接执行搜索
-    raw_results = tavily_tool.run(text)
-    search_results = [{k: v for k, v in item.items() if k != 'url'} for item in raw_results]
-
-    # print("=== 完整搜索返回值 ===")
-    # print(search_results)
-    return search_results
-
-
-def zhipu_search(text, config, top_k):
-    api_key = config["zhipu_api_key"]
-    endpoint = "https://open.bigmodel.cn/api/paas/v4/web_search"
-    headers = {
-        "Authorization": f"Bearer {api_key}",
-        "Content-Type": "application/json"
-    }
-    payload = {
-        "search_engine": "Search-Pro",  # 指定Web搜索专用模型
-        "search_query": text
-    }
-    response = requests.post(endpoint, headers=headers, json=payload)
-    result = response.json()
-    print(f"================!! result: {result}")
-    return result
-
-
 SEARCH_ENGINES = {
     "bing": bing_search,
     "duckduckgo": duckduckgo_search,
     "metaphor": metaphor_search,
     "searx": searx_search,
-    "tavily": tavily_search,
-    "zhipu_search": zhipu_search
 }
 
 
-def search_result2docs(search_results, engine_name, top_k) -> List[Document]:
+def search_result2docs(search_results) -> List[Document]:
     docs = []
-    if engine_name == "zhipu_search":
-        try:
-            # search_results_json = json.loads(search_results)
-            results = search_results["search_result"]
-        except (KeyError, IndexError) as e:
-            print(f"结构异常: {e}")
-            results = []
-        # 遍历并处理每个结果
-        for item in results[:top_k]:
-            doc = Document(
-                page_content=item['content'],
-                metadata={"link": item['link'], "title": item['title']}
-            )
-            docs.append(doc)
-        return docs
-    page_contents_key = "snippet" if engine_name != "tavily" else "content"
-    metadata_key = "link" if engine_name != "tavily" else "url"
     for result in search_results:
         doc = Document(
-            page_content=result[page_contents_key] if page_contents_key in result.keys() else "",
+            page_content=result["snippet"] if "snippet" in result.keys() else "",
             metadata={
-                "source": result[metadata_key] if metadata_key in result.keys() else "",
+                "source": result["link"] if "link" in result.keys() else "",
                 "filename": result["title"] if "title" in result.keys() else "",
             },
         )
@@ -172,7 +107,7 @@ def search_result2docs(search_results, engine_name, top_k) -> List[Document]:
     return docs
 
 
-def search_engine(query: str, top_k: int = 0, engine_name: str = "", config: dict = {}):
+def search_engine(query: str, top_k:int=0, engine_name: str="", config: dict={}):
     config = config or get_tool_config("search_internet")
     if top_k <= 0:
         top_k = config.get("top_k", Settings.kb_settings.SEARCH_ENGINE_TOP_K)
@@ -182,20 +117,12 @@ def search_engine(query: str, top_k: int = 0, engine_name: str = "", config: dic
     results = search_engine_use(
         text=query, config=config["search_engine_config"][engine_name], top_k=top_k
     )
-
+    docs = [x for x in search_result2docs(results) if x.page_content and x.page_content.strip()]
-    docs = [x for x in search_result2docs(results, engine_name, top_k) if x.page_content and x.page_content.strip()]
-    print(f"len(docs): {len(docs)}")
-    # print(f"docs:{docs}")
-    # # print(f"docs: {docs[:150]}")
     return {"docs": docs, "search_engine": engine_name}
 
 
 @regist_tool(title="互联网搜索")
 def search_internet(query: str = Field(description="query for Internet search")):
     """用这个工具实现获取世界、历史、实时新闻、或除电力系统之外的信息查询"""
-    try:
     print(f"search_internet: query: {query}")
-        return BaseToolOutput(data=search_engine(query=query), format=format_context)
+    return BaseToolOutput(search_engine(query=query), format=format_context)
-    except Exception as e:
-        logger.error(f"未知错误: {str(e)}")
-        return BaseToolOutput(f"搜索过程中发生未知错误,{str(e)}", format=format_context)

libs/chatchat-server/chatchat/server/agent/tools_factory/tools_registry.py

@@ -176,7 +176,7 @@ def format_context(self: BaseToolOutput) -> str:
         doc = DocumentWithVSId.parse_obj(doc)
         source_documents.append(doc.page_content)
 
-        # print(f"format_context: doc.page_content: {doc.page_content}")
+        print(f"format_context: doc.page_content: {doc.page_content}")
     if len(source_documents) == 0:
         context = "没有找到相关文档,请更换关键词重试"
     else:

libs/chatchat-server/chatchat/server/agent/tools_factory/weather_check.py

@@ -19,7 +19,7 @@ def weather_check(
                     "- '今天'：获取当前实时天气\n"
                     "- '明天'/'后天'：获取未来24/48小时预报\n"
                     "- '未来X天'：获取最多X天预报（如'未来3天'）,X的抽取要符合客户意图\n"
-                        "- 不支持其他参数，如果是其他参数，则时间参数为None\n"
+                    "- 不支持其他参数，如果是其他参数，则时间参数为None"
     )
 ):
     """用这个工具获取指定地点和指定时间的天气"""
@@ -32,7 +32,8 @@ def weather_check(
         missing_params.append("日期参数")
 
     if missing_params:
-        return BaseToolOutput(data={"error_message": f"缺少必要参数：{', '.join(missing_params)}，请补充完整查询信息"},
+        return BaseToolOutput(
+            error_message=f"缺少必要参数：{', '.join(missing_params)}，请补充完整查询信息",
             require_additional_input=True
         )
 
@@ -41,13 +42,13 @@ def weather_check(
         weather_type, number = parse_date_parameter(date)
     except ValueError as e:
         logging.error(f"日期参数解析失败: {str(e)}")
-        return BaseToolOutput(data={"error_message": str(e)})
+        return BaseToolOutput(str(e))
 
     # 获取API配置
     tool_config = get_tool_config("weather_check")
     api_key = tool_config.get("api_key")
     if not api_key:
-        return BaseToolOutput(data={"error_message": "API密钥未配置，请联系管理员"})
+        return BaseToolOutput("API密钥未配置，请联系管理员")
 
     # 根据天气类型调用API
     if weather_type == "daily":
@@ -55,8 +56,7 @@ def weather_check(
     elif weather_type == "future":
         return _get_future_weather(city, api_key, number)
     else:
-        return BaseToolOutput(data={"error_message": "不支持的天气类型"})
+        return BaseToolOutput("不支持的天气类型")
-
 
 def _get_current_weather(city: str, api_key: str) -> BaseToolOutput:
     """获取当前实时天气"""
@@ -66,15 +66,14 @@ def _get_current_weather(city: str, api_key: str) -> BaseToolOutput:
 
     if response.status_code != 200:
         logging.error(f"天气查询失败: {response.status_code}")
-        return BaseToolOutput(data={"error_message": "天气查询API请求失败"})
+        return BaseToolOutput("天气查询API请求失败")
 
     data = response.json()
     weather = {
         "temperature": data["results"][0]["now"]["temperature"],
         "description": data["results"][0]["now"]["text"],
     }
-    return BaseToolOutput(data=weather)
+    return BaseToolOutput(weather)
-
 
 def _get_future_weather(city: str, api_key: str, days: int) -> BaseToolOutput:
     """获取未来天气预报"""
@@ -116,10 +115,9 @@ def _get_future_weather(city: str, api_key: str, days: int) -> BaseToolOutput:
             "后天最高温度": daily_data[2]["high"],
         }
     else:
-        return BaseToolOutput(data={"error_message": "不支持的天数参数"})
+        return BaseToolOutput("不支持的天数参数")
-
-    return BaseToolOutput(data=weather)
 
+    return BaseToolOutput(weather)
 
 def parse_date_parameter(date: str) -> tuple:
     """解析日期参数，返回天气类型和天数"""
@@ -138,6 +136,5 @@ def parse_date_parameter(date: str) -> tuple:
     else:
         raise ValueError("不支持的日期参数")
 
-
 if __name__ == "__main__":
-    weather_check("合肥", "明天")
+    weather_check("合肥","明天")

libs/chatchat-server/chatchat/server/api_server/chat_routes.py

@@ -65,7 +65,7 @@ async def chat_completions(
     # import rich
     # rich.print(body)
     # 当调用本接口且 body 中没有传入 "max_tokens" 参数时, 默认使用配置中定义的值
-    # logger.info(f"body.model_config:{body.model_config},body.tools: {body.tools},body.messages:{body.messages}")
+    logger.info(f"body.model_config:{body.model_config},body.tools: {body.tools},body.messages:{body.messages}")
     if body.max_tokens in [None, 0]:
         body.max_tokens = Settings.model_settings.MAX_TOKENS
 

libs/chatchat-server/chatchat/server/knowledge_base/utils.py

@@ -70,9 +70,6 @@ def list_files_from_folder(kb_name: str):
         for x in ["temp", "tmp", ".", "~$"]:
             if tail.startswith(x):
                 return True
-        if "_source.txt" in tail.lower() or "_split.txt" in tail.lower():
-            return True
-
         return False
 
     def process_entry(entry):
@@ -425,15 +422,15 @@ class KnowledgeFile:
             docs = zh_first_title_enhance(docs)
             docs = customize_zh_title_enhance(docs)
 
-            i = 1
+            # i = 1
-            outputfile = file_name_without_extension + "_split.txt"
+            # outputfile = file_name_without_extension + "_split.txt"
-            # 打开文件以写入模式
+            # # 打开文件以写入模式
-            with open(outputfile, 'w') as file:
+            # with open(outputfile, 'w') as file:
-                for doc in docs:
+            #     for doc in docs:
-                    #print(f"**********切分段{i}：{doc}")
+            #         #print(f"**********切分段{i}：{doc}")
-                    file.write(f"\n**********切分段{i}")
+            #         file.write(f"\n**********切分段{i}")
-                    file.write(doc.page_content)
+            #         file.write(doc.page_content)
-                    i = i+1
+            #         i = i+1
 
         self.splited_docs = docs
         return self.splited_docs

libs/chatchat-server/chatchat/settings.py

@@ -488,7 +488,7 @@ class ToolSettings(BaseFileSettings):
 
     search_internet: dict = {
         "use": False,
-        "search_engine_name": "zhipu_search",
+        "search_engine_name": "duckduckgo",
         "search_engine_config": {
             "bing": {
                 "bing_search_url": "https://api.bing.microsoft.com/v7.0/search",
@@ -506,21 +506,11 @@ class ToolSettings(BaseFileSettings):
                 "engines": [],
                 "categories": [],
                 "language": "zh-CN",
-            },
-            "tavily":{
-                "tavily_api_key": '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',
-                "include_answer": True,
-                "search_depth": "advanced",
-                "include_raw_content": True,
-                "max_results": 1
-            },
-            "zhipu_search":{
-                "zhipu_api_key": ""
             }
         },
-        "top_k": 1,
+        "top_k": 5,
         "verbose": "Origin",
-        "conclude_prompt": "<指令>这是搜索到的互联网信息，请你根据这些信息进行提取并有调理，简洁的回答问题,不得包含有重复的词汇或句子。如果无法从中得到答案，请说 “无法搜索到能回答问题的内容”。 "
+        "conclude_prompt": "<指令>这是搜索到的互联网信息，请你根据这些信息进行提取并有调理，简洁的回答问题。如果无法从中得到答案，请说 “无法搜索到能回答问题的内容”。 "
         "</指令>\n<已知信息>{{ context }}</已知信息>\n"
         "<问题>\n"
         "{{ question }}\n"
@@ -660,7 +650,7 @@ class PromptSettings(BaseFileSettings):
 
     rag: dict = {
         "default": (
-            "【指令】根据已知信息，简洁和专业的来回答问题,不得包含有重复的词汇或句子。"
+            "【指令】根据已知信息，简洁和专业的来回答问题。"
             "如果无法从中得到答案，请说 “根据已知信息无法回答该问题”，不允许在答案中添加编造成分，答案请使用中文。\n\n"
             "【已知信息】{{context}}\n\n"
             "【问题】{{question}}\n"
@@ -751,8 +741,6 @@ class PromptSettings(BaseFileSettings):
             "Begin!\n\n"
             "Question: {input}\n\n"
             "{agent_scratchpad}\n\n"
-            "Important: After the last Observation, you must always add a Final Answer "
-            "summarizing the result. Do not skip this step."
             ),
         "structured-chat-agent": (
             "Respond to the human as helpfully and accurately as possible. You have access to the following tools:\n\n"

libs/chatchat-server/chatchat/webui_pages/knowledge_base/knowledge_base.py

@@ -238,7 +238,7 @@ def knowledge_base_page(api: ApiRequest, is_lite: bool = None):
                 doc_details,
                 {
                     ("No", "序号"): {},
-                    ("file_name", "文档名称"): {"filter": "agTextColumnFilter"},
+                    ("file_name", "文档名称"): {},
                     # ("file_ext", "文档类型"): {},
                     # ("file_version", "文档版本"): {},
                     ("document_loader", "文档加载器"): {},